Researchers aiming to increase accuracy in object detection generally enlarge the network, but that approach also boosts computational cost. A novel architecture sets a new state of the art in accuracy while cutting the compute cycles required.

The previous state-of-the-art image classifier was trained on the ImageNet dataset plus 3.5 billion supplemental images from a different database. A new method achieved higher accuracy with one-tenth as many supplemental examples — and they were unlabeled, to boot.

Reinforcement learning trains models by trial and error. In batch reinforcement learning (BRL), models learn by observing many demonstrations by a variety of actors. But what if one doctor is handier with a scalpel while another excels at suturing?

Automatically generated text summaries are becoming common in search engines and news websites. But existing summarizers often mix up facts. For instance, a victim’s name might get switched for the perpetrator’s.

In reinforcement learning, if researchers want an agent to have an internal representation of its environment, they’ll build and train a world model that it can refer to. New research shows that world models can emerge from standard training, rather than needing to be built separately.

Sophisticated models trained on biased data can learn discriminatory patterns, which leads to skewed decisions. A new solution aims to prevent neural networks from making decisions based on common biases.

Models that summarize documents and answer questions work pretty well with limited source material, but they can slip into incoherence when they draw from a sizeable corpus. Recent work addresses this problem.

As black-box algorithms like neural networks find their way into high-stakes fields such as transportation, healthcare, and finance, researchers have developed techniques to help explain models’ decisions. New findings show that some of these methods can be fooled.

Large NLP models like BERT can answer questions about a document thanks to the transformer network, a sequence-processing architecture that retains information across much longer sequences than previous methods. But transformers have had little success in reinforcement learning — until now.

Computer vision models typically draw bounding boxes around objects they spot, but those rectangles are a crude approximation of an object’s outline. A new method finds keypoints on an object’s perimeter to produce state-of-the-art object classification.

Predicting a molecule’s aroma is hard because slight changes in structure lead to huge shifts in perception. Good thing deep learning is developing a sense of smell.

A word-embedding model typically learns vector representations from a large, general-purpose corpus like Google News. But to make the resulting vectors useful in a specialized domain, they must be fine-tuned on a smaller, domain-specific dataset. Researchers offer a more accurate method.

Looking at images, people see outlines before the details within them. A replacement for the traditional convolutional layer decomposes images based on this distinction between coarse and fine features.

Generative networks can embroider sentences into stories and melodies into full-fledged arrangements. A new model does something similar with drawings.

Robots designed to assist people with disabilities have become more capable, but they’ve also become harder to control. New research offers a way to operate such complex mechanical systems more intuitively.